原书出处
Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications
data versatility, requiring their data to be fixed. Moreover, Standard Recurrent Neural Networks (RNNs) have constraints as future data information can’t emerge out of the current state. Notwithstanding what may be normal, Bi-directional recurrent neural networks don’t need their data to be fixed. Furthermore, their future data information is reachable from the current state. The Bi-Directional Long Short-Term Memory has been shown in Fig. (6).
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications/_epub-src/OEBPS/Text/9789815136746-C7.html
EPUB SHA-256:07af1c60f26fc108987377a240ac647de87c7bcb3ac93cb62d00223c0ce2a956